Validation of a Machine Learning Expert Supporting System, ImmunoGenius, Using Immunohistochemistry Results of 3000 Patients with Lymphoid Neoplasms
(1) Background: Differential diagnosis using immunohistochemistry (IHC) panels is a crucial step in the pathological diagnosis of hematolymphoid neoplasms. In this study, we evaluated the prediction accuracy of the ImmunoGenius software using nationwide data to validate its clinical utility. (2) Met...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/7/1308 |
| _version_ | 1797608208332750848 |
|---|---|
| author | Jamshid Abdul-Ghafar Kyung Jin Seo Hye-Ra Jung Gyeongsin Park Seung-Sook Lee Yosep Chong |
| author_facet | Jamshid Abdul-Ghafar Kyung Jin Seo Hye-Ra Jung Gyeongsin Park Seung-Sook Lee Yosep Chong |
| author_sort | Jamshid Abdul-Ghafar |
| collection | DOAJ |
| description | (1) Background: Differential diagnosis using immunohistochemistry (IHC) panels is a crucial step in the pathological diagnosis of hematolymphoid neoplasms. In this study, we evaluated the prediction accuracy of the ImmunoGenius software using nationwide data to validate its clinical utility. (2) Methods: We collected pathologically confirmed lymphoid neoplasms and their corresponding IHC results from 25 major university hospitals in Korea between 2015 and 2016. We tested ImmunoGenius using these real IHC panel data and compared the precision hit rate with previously reported diagnoses. (3) Results: We enrolled 3052 cases of lymphoid neoplasms with an average of 8.3 IHC results. The precision hit rate was 84.5% for these cases, whereas it was 95.0% for 984 in-house cases. (4) Discussion: ImmunoGenius showed excellent results in most B-cell lymphomas and generally showed equivalent performance in T-cell lymphomas. The primary reasons for inaccurate precision were atypical IHC profiles of certain cases, lack of disease-specific markers, and overlapping IHC profiles of similar diseases. We verified that the machine-learning algorithm could be applied for diagnosis precision with a generally acceptable hit rate in a nationwide dataset. Clinical and histological features should also be taken into account for the proper use of this system in the decision-making process. |
| first_indexed | 2024-03-11T05:40:11Z |
| format | Article |
| id | doaj.art-c35ea61e9e7e43878581c3dd27f22acc |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T05:40:11Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-c35ea61e9e7e43878581c3dd27f22acc2023-11-17T16:30:46ZengMDPI AGDiagnostics2075-44182023-03-01137130810.3390/diagnostics13071308Validation of a Machine Learning Expert Supporting System, ImmunoGenius, Using Immunohistochemistry Results of 3000 Patients with Lymphoid NeoplasmsJamshid Abdul-Ghafar0Kyung Jin Seo1Hye-Ra Jung2Gyeongsin Park3Seung-Sook Lee4Yosep Chong5Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of KoreaDepartment of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of KoreaDepartment of Pathology, Keimyung University, Daegu 42601, Republic of KoreaDepartment of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of KoreaDepartment of Pathology, Korea Institute of Radiological and Medical Sciences, Seoul 01812, Republic of KoreaDepartment of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea(1) Background: Differential diagnosis using immunohistochemistry (IHC) panels is a crucial step in the pathological diagnosis of hematolymphoid neoplasms. In this study, we evaluated the prediction accuracy of the ImmunoGenius software using nationwide data to validate its clinical utility. (2) Methods: We collected pathologically confirmed lymphoid neoplasms and their corresponding IHC results from 25 major university hospitals in Korea between 2015 and 2016. We tested ImmunoGenius using these real IHC panel data and compared the precision hit rate with previously reported diagnoses. (3) Results: We enrolled 3052 cases of lymphoid neoplasms with an average of 8.3 IHC results. The precision hit rate was 84.5% for these cases, whereas it was 95.0% for 984 in-house cases. (4) Discussion: ImmunoGenius showed excellent results in most B-cell lymphomas and generally showed equivalent performance in T-cell lymphomas. The primary reasons for inaccurate precision were atypical IHC profiles of certain cases, lack of disease-specific markers, and overlapping IHC profiles of similar diseases. We verified that the machine-learning algorithm could be applied for diagnosis precision with a generally acceptable hit rate in a nationwide dataset. Clinical and histological features should also be taken into account for the proper use of this system in the decision-making process.https://www.mdpi.com/2075-4418/13/7/1308databaseexpert supporting systemmachine learningimmunohistochemistryprobabilistic decision tree |
| spellingShingle | Jamshid Abdul-Ghafar Kyung Jin Seo Hye-Ra Jung Gyeongsin Park Seung-Sook Lee Yosep Chong Validation of a Machine Learning Expert Supporting System, ImmunoGenius, Using Immunohistochemistry Results of 3000 Patients with Lymphoid Neoplasms Diagnostics database expert supporting system machine learning immunohistochemistry probabilistic decision tree |
| title | Validation of a Machine Learning Expert Supporting System, ImmunoGenius, Using Immunohistochemistry Results of 3000 Patients with Lymphoid Neoplasms |
| title_full | Validation of a Machine Learning Expert Supporting System, ImmunoGenius, Using Immunohistochemistry Results of 3000 Patients with Lymphoid Neoplasms |
| title_fullStr | Validation of a Machine Learning Expert Supporting System, ImmunoGenius, Using Immunohistochemistry Results of 3000 Patients with Lymphoid Neoplasms |
| title_full_unstemmed | Validation of a Machine Learning Expert Supporting System, ImmunoGenius, Using Immunohistochemistry Results of 3000 Patients with Lymphoid Neoplasms |
| title_short | Validation of a Machine Learning Expert Supporting System, ImmunoGenius, Using Immunohistochemistry Results of 3000 Patients with Lymphoid Neoplasms |
| title_sort | validation of a machine learning expert supporting system immunogenius using immunohistochemistry results of 3000 patients with lymphoid neoplasms |
| topic | database expert supporting system machine learning immunohistochemistry probabilistic decision tree |
| url | https://www.mdpi.com/2075-4418/13/7/1308 |
| work_keys_str_mv | AT jamshidabdulghafar validationofamachinelearningexpertsupportingsystemimmunogeniususingimmunohistochemistryresultsof3000patientswithlymphoidneoplasms AT kyungjinseo validationofamachinelearningexpertsupportingsystemimmunogeniususingimmunohistochemistryresultsof3000patientswithlymphoidneoplasms AT hyerajung validationofamachinelearningexpertsupportingsystemimmunogeniususingimmunohistochemistryresultsof3000patientswithlymphoidneoplasms AT gyeongsinpark validationofamachinelearningexpertsupportingsystemimmunogeniususingimmunohistochemistryresultsof3000patientswithlymphoidneoplasms AT seungsooklee validationofamachinelearningexpertsupportingsystemimmunogeniususingimmunohistochemistryresultsof3000patientswithlymphoidneoplasms AT yosepchong validationofamachinelearningexpertsupportingsystemimmunogeniususingimmunohistochemistryresultsof3000patientswithlymphoidneoplasms |